A data-driven sender can learn a near-optimal decision-calibrated predictor without knowing the prior, but the proof as written has a critical Lagrangian error and the Bayesian benchmark is restricted by construction.
Efficient prior-free mechanisms for no-regret agents
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GT 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Persuasive Prediction via Decision Calibration
A data-driven sender can learn a near-optimal decision-calibrated predictor without knowing the prior, but the proof as written has a critical Lagrangian error and the Bayesian benchmark is restricted by construction.